An Intra-Day Electricity Price Forecasting Based on a Probabilistic Transformer Neural Network Architecture

Abstract

This paper describes the development of a deep neural network architecture based on transformer encoder blocks and Time2Vec layers for the prediction of electricity prices several steps ahead (8 h), from a probabilistic approach, to feed future decision-making tools in the context of the widespread use of intra-day DERs and new market perspectives. The proposed model was tested with hourly wholesale electricity price data from Colombia, and the results were compared with different state-of-the-art forecasting baseline-tuned models such as Holt–Winters, XGBoost, Stacked LSTM, and Attention-LSTM. The findings show that the proposed model outperforms these baselines by effectively incorporating nonlinearity and explicitly modeling the underlying data’s behavior, all of this under four operating scenarios and different performance metrics. This allows it to handle high-, medium-, and low-variability scenarios while maintaining the accuracy and reliability of its predictions. The proposed framework shows potential for significantly improving the accuracy of electricity price forecasts, which can have significant benefits for making informed decisions in the energy sector.

A Stochastic Decision-Making Tool Suite for Distributed Energy Resources Integration in Energy Markets

“…First, time series models can capture complex temporal patterns and dependencies, thereby enabling more accurate forecasts and the quantification of uncertainty, particularly in the case of variables that exhibit seasonality, trends, or time-varying features [76,77]. Second, these models can generate probabilistic forecasts, providing not only point estimates but also confidence intervals or probability distributions, which can be directly integrated into uncertainty-handling methods.…”

“…For day-ahead market prices, the Time2Vec Transformer Encoder (T2V-TE) forecasting model is used. It is based on transformer encoders and enhanced with capabilities to capture short and long-term temporal dependencies, such as Time2Vec [82] introduced in [76]. It provides an interval probabilistic forecast in the first stage.…”